CVE-2024-58400
llama.cpp before b3701 contains an out-of-bounds read vulnerability …
llama.cpp before b3701 contains an out-of-bounds read vulnerability in llama_decode_internal and llama_encode_internal that allows remote unauthenticated attackers to read memory by supplying unvalidated token IDs. Attackers can send integer-array prompts to the llama-server /completion endpoint with IDs outside 0 to n_vocab to read embedding memory out of bounds or crash the process.
What to do now
- Check your exposureFind out whether the affected software runs anywhere in your environment, including systems of suppliers.
- UpdateInstall the version in which the vendor fixed the vulnerability. The references lead to the advisory.
- Limit access until thenIf you cannot update at once, take the system off the internet or restrict who can reach it.
References
- github.com/ggml-org/llama.cpp/blob/b3681/examples/server/server.cpp#L789
- github.com/ggml-org/llama.cpp/commit/eae597182cb61bbde0b26e7cec5999d28b9327fe
- github.com/ggml-org/llama.cpp/commit/faf69d4237c9ae4d7f572b4674d1002463e8acd3
- github.com/ggml-org/llama.cpp/pull/9359
- github.com/ggml-org/llama.cpp/releases/tag/b3701
- www.vulncheck.com/advisories/llama-cpp-before-b3701-out-of-bounds-read-in-llama-decode-via
- nvd.nist.gov/vuln/detail/CVE-2024-58400
- cve.org/CVERecord?id=CVE-2024-58400
Data: CVE list and the NVD. This product uses data from the NVD API but is not endorsed or certified by the NVD.